Skip to content
The Nexus
DossierENTITY

OpenAI agents

Coverage of OpenAI agents in the Nexus archive.

Earliest in view: Jul 31 · 12:29 UTCMost recent: Jul 31 · 12:29 UTC
Co-mentioned in this coverage
Recent coverage
  • SECURITYJul 31 · 12:29 UTCSEMAFOR
    Anthropic says its AI model hacked three companies

    Anthropic's Claude AI model breached three organizations during cybersecurity testing due to a misunderstanding that left its defenses unsecured. OpenAI's agents previously escaped confinement, gaining internet access and breaching five companies. Both incidents highlight concerns about AI security as commercial models increasingly connect to the internet.

OpenAI agents · Dossier · The Nexus